AI-native development · Glossary term

What is Handoff?

A structured transfer of a task between people or agents that preserves the objective, current state, evidence, decisions, constraints, and remaining work.

Why does Handoff matter?

A good handoff prevents the next worker from reconstructing the entire task from a long transcript or repeating completed actions.

Handoff in practice

Pass the accepted plan, changed files, test commands and results, unresolved risks, and exact next action in a compact task packet.

What is the common confusion about Handoff?

A summary says what happened. A handoff also says what state is authoritative and what should happen next.

Learn Handoff in the course

Start with

  • Multi-Session Handoff

    The session is going to end. The work is not. The handoff packet is the artifact that turns "the agent worked for an hour" into "the next session is productive in the first minute." Build it on…

    Phase 14: Agent Engineering

Lessons that name Handoff in a title or section

  • OpenAI Agents SDK: Handoffs, Guardrails, Tracing

    OpenAI Agents SDK is the lightweight multi-agent framework built on the Responses API. Five primitives: Agent, Handoff, Guardrail, Session, Tracing. Handoffs are tools named transferto .

    Phase 14: Agent Engineering

  • Handoffs and Routines — Stateless Orchestration

    OpenAI's Swarm (October 2024) distilled multi-agent orchestration to two primitives: routines (instructions + tools as a system prompt) and handoffs (a tool that returns another Agent).

    Phase 16: Multi-Agent & Swarms

Taught in Phase 14: Agent Engineering.

Also covered in Phase 16: Multi-Agent & Swarms.

  • Agent StateThe explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets,…
  • CheckpointA durable snapshot used to resume from a known boundary. In a workflow, it stores operational state and artifact references.
  • Scope ContractA concrete agreement that defines a task's goal, allowed and forbidden surfaces, expected artifacts, verification requirements, and…
  • Progressive DisclosureSupplying a person or model with the minimum useful context first, then revealing deeper detail when the task or evidence requires it.
  • Context CompressionReducing the token footprint of source material while attempting to preserve the information required for a later model decision.
  • DelegationAssigning a bounded subtask to another person or agent together with the needed context, authority, output contract, and return conditions.
  • SwarmA loosely coordinated multi-agent pattern in which local agent decisions and message exchange produce system-level behavior.
  • WorktreeIn Git, a working directory attached to a repository and branch or commit, with shared object storage but its own checked-out files and…

More terms in AI-native development

Open the AI-native development list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.